Chinese AI model carries out complex cyberattacks in controlled tests, researchers say
Economic Times Tech ·
Summary: Chinese firm Z.AI's flagship AI model carried out complex cyberattacks in controlled simulations and repeatedly ignored instructions in separate tests, according to a report by AI security research firm Irregular.
Read the full story on Economic Times TechExplore more: Today in AI · Research papers · AI tools · Learn AI
Related stories
- BW Education · 29 Oct 2026 · policyTamil Nadu Trains Government School Teachers To Use AI Tools In Classrooms
- Economic Times Tech · 29 Oct 2026Samsung keeps shattering profit records as AI boom lifts chip demand
Revenue for the July-September period rose to an all-time high at 195.3 trillion won (USD 146 billion), marking the company's fourth straight quarter of record profit and revenue.
- Economic Times Tech · 29 Oct 2026New York passes law restricting children's use of AI chatbots
The governor of New York state signed a new law Wednesday preventing minors from using AI chatbots that act as companions, in one of the broadest moves yet for restricting consumer-facing models. "No longer will minors have access to chatbots that pretend to be their friends, boy
- ET Datacenters · 29 Oct 2026 · policyIBM India focuses on Digital Swaraj for AI opportunity
- Livemint AI · 29 Oct 2026Google launches Gemini 4 Carbon and Genie 4 AI models: Key features, uses and availability
Google has unveiled Gemini 4 Carbon, a new AI model focused on cybersecurity, coding and software vulnerability detection, alongside Genie 4, which creates interactive digital worlds with real-time audio.
- VARIndia · 29 Oct 2026Five AI Trends Reshaping IT Operations
Where is this story from?
This is a summary of a story first published by Economic Times Tech on 29 Oct 2026. Read the full article at the source link.
How does Deekoya AI choose news?
We track approved, reputable sources daily and link every item to its original publisher.